© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 1302
    Prev
    Next
    INDEX
    Explanations

    family relationships and information related to obituaries

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.24
    1.0%
    453
    +0.12
    0.5%
    498
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    498
    +0.24
    0.05
    1012
    +0.12
    0.04
    509
    +0.06
    0.04
    Negative Logits
    <bos>
    -1.50
    ⓧ
    -0.82
    <?
    -0.77
    /*
    -0.68
    /**
    -0.67
    /*++
    -0.66
     themselves
    -0.62
     itself
    -0.61
    
    -0.59
     effectively
    -0.57
    POSITIVE LOGITS
     maneu
    1.40
     véhic
    1.39
     accla
    1.36
     reluct
    1.31
     Keny
    1.28
     Minang
    1.26
     soulign
    1.23
     strick
    1.23
     stockholm
    1.21
     increa
    1.20
    Activations Density 0.205%

    No Known Activations